All Projects → wataruhashimoto52 → Seq2Seq-chatbot

wataruhashimoto52 / Seq2Seq-chatbot

Licence: other
TensorFlow Implementation of Twitter Chatbot

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Seq2Seq-chatbot

Conversational-AI-Chatbot-using-Practical-Seq2Seq
A simple open domain generative based chatbot based on Recurrent Neural Networks
Stars: ✭ 17 (-5.56%)
Mutual labels:  recurrent-neural-networks, seq2seq
Mead Baseline
Deep-Learning Model Exploration and Development for NLP
Stars: ✭ 238 (+1222.22%)
Mutual labels:  recurrent-neural-networks, seq2seq
Deep-Learning-Tensorflow
Gathers Tensorflow deep learning models.
Stars: ✭ 50 (+177.78%)
Mutual labels:  recurrent-neural-networks, seq2seq
dts
A Keras library for multi-step time-series forecasting.
Stars: ✭ 130 (+622.22%)
Mutual labels:  recurrent-neural-networks, seq2seq
ai-visual-storytelling-seq2seq
Implementation of seq2seq model for Visual Storytelling Challenge (VIST) http://visionandlanguage.net/VIST/index.html
Stars: ✭ 50 (+177.78%)
Mutual labels:  recurrent-neural-networks, seq2seq
Text Classification Models Pytorch
Implementation of State-of-the-art Text Classification Models in Pytorch
Stars: ✭ 379 (+2005.56%)
Mutual labels:  recurrent-neural-networks, seq2seq
Komputation
Komputation is a neural network framework for the Java Virtual Machine written in Kotlin and CUDA C.
Stars: ✭ 295 (+1538.89%)
Mutual labels:  recurrent-neural-networks, seq2seq
Deep News Summarization
News summarization using sequence to sequence model with attention in TensorFlow.
Stars: ✭ 167 (+827.78%)
Mutual labels:  recurrent-neural-networks, seq2seq
Variational Recurrent Autoencoder Tensorflow
A tensorflow implementation of "Generating Sentences from a Continuous Space"
Stars: ✭ 228 (+1166.67%)
Mutual labels:  recurrent-neural-networks
Awesome Tensorlayer
A curated list of dedicated resources and applications
Stars: ✭ 248 (+1277.78%)
Mutual labels:  recurrent-neural-networks
Rnn ctc
Recurrent Neural Network and Long Short Term Memory (LSTM) with Connectionist Temporal Classification implemented in Theano. Includes a Toy training example.
Stars: ✭ 220 (+1122.22%)
Mutual labels:  recurrent-neural-networks
Echotorch
A Python toolkit for Reservoir Computing and Echo State Network experimentation based on pyTorch. EchoTorch is the only Python module available to easily create Deep Reservoir Computing models.
Stars: ✭ 231 (+1183.33%)
Mutual labels:  recurrent-neural-networks
chatbot
Seq2Seq Chatbot with attention mechanism
Stars: ✭ 19 (+5.56%)
Mutual labels:  seq2seq
Cs224d
Code for Stanford CS224D: deep learning for natural language understanding
Stars: ✭ 222 (+1133.33%)
Mutual labels:  recurrent-neural-networks
Naver-AI-Hackathon-Speech
2019 Clova AI Hackathon : Speech - Rank 12 / Team Kai.Lib
Stars: ✭ 26 (+44.44%)
Mutual labels:  seq2seq
Im2latex Tensorflow
Tensorflow implementation of the HarvardNLP paper - What You Get Is What You See: A Visual Markup Decompiler (https://arxiv.org/pdf/1609.04938v1.pdf)
Stars: ✭ 207 (+1050%)
Mutual labels:  recurrent-neural-networks
SharkStock
Automate swing trading using deep reinforcement learning. The deep deterministic policy gradient-based neural network model trains to choose an action to sell, buy, or hold the stocks to maximize the gain in asset value. The paper also acknowledges the need for a system that predicts the trend in stock value to work along with the reinforcement …
Stars: ✭ 63 (+250%)
Mutual labels:  recurrent-neural-networks
Pytorch Sentiment Analysis
Tutorials on getting started with PyTorch and TorchText for sentiment analysis.
Stars: ✭ 3,209 (+17727.78%)
Mutual labels:  recurrent-neural-networks
Attention Mechanisms
Implementations for a family of attention mechanisms, suitable for all kinds of natural language processing tasks and compatible with TensorFlow 2.0 and Keras.
Stars: ✭ 203 (+1027.78%)
Mutual labels:  recurrent-neural-networks
Relational Rnn Pytorch
An implementation of DeepMind's Relational Recurrent Neural Networks in PyTorch.
Stars: ✭ 236 (+1211.11%)
Mutual labels:  recurrent-neural-networks

Seq2Seq chatbot (ja)

Overview

Description

This is seq2seq chatbot.

Requirement

python 3.5.2
Tensorflow r1.2
Mecab
tweepy

Demo

  1. Prepare train data.

    1, Registration to the Twitter API(https://apps.twitter.com).

    2, Extraction of consumerkey, consumer secret key, access token key and access token secret key.

    3, Installation forego.

    $ brew install forego

    Then, please make .env file and write consumerkey, consumer secret key, access token key and access token secret key.

    $ vi .env

    CONSUMER_KEY=...
    CONSUMER_SECRET=...
    ACCESS_TOKEN=...
    ACCESS_TOKEN_SECRET=...
    

    4, $ forego run python twitter_replies.py

  2. Preprocess the train data and generate vocabulary files, ID files, and some ones.

    $ python data_processor.py

  3. Train seq2seq chatbot. When perplexity went down sufficiently and you think it's time to run, just ctrl-c to stop learning.

    $ python train.py

  4. Let's talk to him.

    $ python predict.py

Contribution

Author

[wataruhashimoto52] https://github.com/wataruhashimoto52

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].